Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.debian.user > #230619 > unrolled thread
| Started by | Dennis Wicks <wix@mgssub.com> |
|---|---|
| First post | 2021-01-13 20:10 +0100 |
| Last post | 2021-01-14 19:00 +0100 |
| Articles | 3 on this page of 23 — 10 participants |
Back to article view | Back to linux.debian.user
Disk errors ... Dennis Wicks <wix@mgssub.com> - 2021-01-13 20:10 +0100
Re: Disk errors ... David Christensen <dpchrist@holgerdanske.com> - 2021-01-13 23:00 +0100
Re: Disk errors ... Michael Stone <mstone@debian.org> - 2021-01-13 23:40 +0100
Re: Disk errors ... David Christensen <dpchrist@holgerdanske.com> - 2021-01-14 00:00 +0100
Re: Disk errors ... Michael Howard <mike@dewberryfields.co.uk> - 2021-01-14 00:00 +0100
Re: old red cables cause Disk errors ... Felix Miata <mrmazda@earthlink.net> - 2021-01-14 00:30 +0100
Re: old red cables cause Disk errors ... Dennis Wicks <wix@mgssub.com> - 2021-01-14 00:50 +0100
Re: old red cables cause Disk errors ... Gene Heskett <gheskett@shentel.net> - 2021-01-14 01:10 +0100
Re: old red cables cause Disk errors ... Michael Stone <mstone@debian.org> - 2021-01-14 01:10 +0100
Re: old red cables cause Disk errors ... Michael Stone <mstone@debian.org> - 2021-01-14 01:30 +0100
Re: old red cables cause Disk errors ... David Christensen <dpchrist@holgerdanske.com> - 2021-01-14 01:10 +0100
Re: old red cables cause Disk errors ... Felix Miata <mrmazda@earthlink.net> - 2021-01-14 01:30 +0100
Re: Disk errors ... Michael Stone <mstone@debian.org> - 2021-01-14 00:20 +0100
Re: Disk errors ... Charles Curley <charlescurley@charlescurley.com> - 2021-01-14 01:20 +0100
Re: Disk errors ... Joe <joe@jretrading.com> - 2021-01-14 10:10 +0100
Re: Disk errors ... Dominique Dumont <dod@debian.org> - 2021-01-17 12:50 +0100
Re: Disk errors ... Gene Heskett <gheskett@shentel.net> - 2021-01-14 00:40 +0100
Re: Disk errors ... David Christensen <dpchrist@holgerdanske.com> - 2021-01-14 01:10 +0100
Re: Disk errors ... Charles Curley <charlescurley@charlescurley.com> - 2021-01-14 01:20 +0100
Re: Disk errors ... Miles Fidelman <mfidelman@meetinghouse.net> - 2021-01-14 18:00 +0100
Re: Disk errors ... Michael Stone <mstone@debian.org> - 2021-01-14 18:10 +0100
Re: Disk errors ... Miles Fidelman <mfidelman@meetinghouse.net> - 2021-01-14 18:50 +0100
Re: Disk errors ... Michael Stone <mstone@debian.org> - 2021-01-14 19:00 +0100
Page 2 of 2 — ← Prev page 1 [2]
| From | Michael Stone <mstone@debian.org> |
|---|---|
| Date | 2021-01-14 18:10 +0100 |
| Message-ID | <Bxeid-31k-3@gated-at.bofh.it> |
| In reply to | #230672 |
On Thu, Jan 14, 2021 at 11:45:25AM -0500, Miles Fidelman wrote: >Dennis Wicks wrote: >>Greetings; >> >>I am getting very frequent disk errors and I can't figure out which >>drive they are occurring on. I get two messages: >> >>>[174384.704895] sata_sil 0000:05:00.0: Event logged [IO_PAGE_FAULT >>>domain=0x0000 address=0x00000000cf99c100 flags=0x0000] >> >>>[174384.705153] AMD-Vi: Event logged [IO_PAGE_FAULT device=05:00.0 >>>domain=0x0000 address=0x00000000df853000 flags=0x0000] >> >>Several of each of them occur at once, every few seconds. >>Is there any way that I can figure out which drive is causing the >>problem? >> >1. Run diagnostics on each drive (say, the SMART long diagnostic) - >that should get you the disk id >2. Run the diagnostics again, on just your failing drive, look for the >drive with the flashing light >3. Depending on how old the drive is, your problem is probably a >failing drive Again, this is a PCI error, not a disk error. I think the OP never did specify the CPU & motherboard? There have been hard to track down AMD IOMMU issues with symptoms like this, I'd pursue that long before I'd run disk scans.
[toc] | [prev] | [next] | [standalone]
| From | Miles Fidelman <mfidelman@meetinghouse.net> |
|---|---|
| Date | 2021-01-14 18:50 +0100 |
| Message-ID | <BxeUW-3dy-9@gated-at.bofh.it> |
| In reply to | #230673 |
Michael Stone wrote: > On Thu, Jan 14, 2021 at 11:45:25AM -0500, Miles Fidelman wrote: >> Dennis Wicks wrote: >>> Greetings; >>> >>> I am getting very frequent disk errors and I can't figure out which >>> drive they are occurring on. I get two messages: >>> >>>> [174384.704895] sata_sil 0000:05:00.0: Event logged [IO_PAGE_FAULT >>>> domain=0x0000 address=0x00000000cf99c100 flags=0x0000] >>> >>>> [174384.705153] AMD-Vi: Event logged [IO_PAGE_FAULT device=05:00.0 >>>> domain=0x0000 address=0x00000000df853000 flags=0x0000] >>> >>> Several of each of them occur at once, every few seconds. >>> Is there any way that I can figure out which drive is causing the >>> problem? >>> >> 1. Run diagnostics on each drive (say, the SMART long diagnostic) - >> that should get you the disk id >> 2. Run the diagnostics again, on just your failing drive, look for >> the drive with the flashing light >> 3. Depending on how old the drive is, your problem is probably a >> failing drive > > Again, this is a PCI error, not a disk error. I think the OP never did > specify the CPU & motherboard? There have been hard to track down AMD > IOMMU issues with symptoms like this, I'd pursue that long before I'd > run disk scans. I agree - probably not a disk error - though it never hurts to check one's drives every once in a while. What makes you think it's a PCI error? A quick google shows that this particular error has been associated with various configuration issues & driver bugs - particularly related to NVIDIA cards. Perhaps a pointer to the documentation on the specific driver reporting the error? (Personally "page fault" could well just indicate normal swapping behavior under load.) -- In theory, there is no difference between theory and practice. In practice, there is. .... Yogi Berra Theory is when you know everything but nothing works. Practice is when everything works but no one knows why. In our lab, theory and practice are combined: nothing works and no one knows why. ... unknown
[toc] | [prev] | [next] | [standalone]
| From | Michael Stone <mstone@debian.org> |
|---|---|
| Date | 2021-01-14 19:00 +0100 |
| Message-ID | <Bxf4B-3gJ-5@gated-at.bofh.it> |
| In reply to | #230675 |
On Thu, Jan 14, 2021 at 12:45:56PM -0500, Miles Fidelman wrote: >I agree - probably not a disk error - though it never hurts to check >one's drives every once in a while. I can think of a very long list of things that are good to do or can't hurt on a debian system. Enumerating them in response to a question when they're unlikely to address the issue seems like a distraction at best.
[toc] | [prev] | [standalone]
Page 2 of 2 — ← Prev page 1 [2]
Back to top | Article view | linux.debian.user
csiph-web